Abstract
The highlights in the digital images, which are from specular reflections on the surface of the object, are inevitable in the real world. It leads to erroneous results in many image processing algorithms. A specular highlight removal model based on a divide-and-conquer multi-resolution deep network is proposed according to the relation between the image patch and its corresponding maximum diffuse chromaticity. We use a Laplacian pyramid to decompose the image patch into two levels, including the same-sized patch with high- frequency components and the low-resolution blurred patch. The former exploits image textures and preserves local structures, and the latter preserves local intensity. Then we design different sub-networks to extract features for the two levels in a divide-and-conquer way and then fuse the features to achieve each pixel’s maximum diffuse chromaticity. Unlike the state-of-the-art methods where the model is trained in an image space, the proposed model for highlight removal based on the dichromatic reflection model is trained in a patch space. Experimental results demonstrate the proposed model is superior or competitive to the existing methods.
Similar content being viewed by others
Data Availability
The data supporting the findings of this study are available from the corresponding author on request.
Notes
We thank the author of [37] for providing source codes for literatures. https://github.com/vitorsr/SIHR
References
Abadi M, Agarwal A, Barham P et al (2016) Tensorflow: Largescale machine learning on heterogeneous distributed systems. https://arxiv.org/abs/1603.04467. Accessed 28 May 2021
Akashi Y, Okatani T (2016) Separation of reflection components by sparse nonnegative matrix factorization. Comput Vis Image Underst 146:77–85
Bajcsy S W, Lee R, Leonardis A (1996) Detection of diffuse and specular interface reflections and inter-reflections by color image segmentation. Int J Comput Vis 17:241–272
Chen F, Ma J (2009) An empirical identification method of gaussian blur parameter for image deblurring. IEEE Trans Signal Process 57:2467–2478
Criminisi A, Kang S B, Swaminathan R, Szeliski R, Anandan P (2005) Extracting layers and analyzing their specular properties using epipolarplane-image analysis. Comput Vis Image Underst 97:51–85
Ephraim Y, Malah D (1984) Speech enhancement using a minimum mean square error log-spectral amplitude estimator. IEEE Trans Acoust Speech Signal Process 32:1109–1121
Fu X, Huang J, Ding X, Liao Y, Paisley J (2017) Clearing the skies: a deep network architecture for single-image rain removal. IEEE Trans Image Process 26:2944–2956
Fu X, Liang B, Huang Y, Ding X, Paisley J (2020) Lightweight pyramid networks for image deraining. IEEE Trans Neural Netw Learn Syst 31:1794–1807
He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: Proc. 2016 IEEE Conference on Computer Vision and Pattern Recognition. IEEE, Los Alamitos, pp 770–778
Huang D A, Kang L W, Wang Y C F, Lin C W (2013) Self-learning based image decomposition with applications to single image denoising. IEEE Trans Multimedia 16:83–93
Karpathy A, Toderici G, Shetty S, Leung T, Sukthankar R, Fei-Fei L (2014) Large-scale video classification with convolutional neural networks. In: Proc. 2014 IEEE Conference on computer vision and pattern recognition. IEEE, Los Alamitos, pp 1725–1732
Keerthi S, Lin C (2003) Asymptotic behaviors of support vector machines with gaussian kernel. Neural Comput 15:1667–1667
Kingma D P, Ba J (2014) Adam: a method for stochastic optimization. https://arxiv.org/pdf/1412.6980.pdf. Accessed 28 May 2021
Klinker G J, Shafer S A, Kanade T (1990) The measurement of highlights in color images. Int J Comput Vis 2:7–32
Krizhevsky A, Sutskever I, Hinton G E (2012) Imagenet classification with deep convolutional neural networks. In: Proc. International conference on neural information processing systems. ACM, New York, pp 1097–1105
Lecun Y, Bengio Y, Hinton G (2015) Deep learning. Nature 521:436–444
Lecun Y, Bottou L, Bengio Y, Haffner P (1998) Gradient-based learning applied to document recognition. In: Proc. of the IEEE, p 2278–2324
Lee S W, Bajcsy R (1992) Detection of specularity using color and multiple views. In: Proc. european conference on computer vision. Springer, New York, pp 99–114
Lin S, Li Y Z, Kang S B, Xin T, Shum H Y (2002) Diffuse-specular separation and depth recovery from image sequences. In: Proc. 7th European conference on computer vision. Springer, New York, pp 210–224
Lin S, Shum H (2001) Separation of diffuse and specular reflection in color images. In: Proc. 2001 IEEE computer society conference on computer vision and pattern recognition. IEEE, Los Alamitos, pp 341–346
Mallick S P, Zickler T, Kriegman D J (2005) Beyond lambert: Reconstructing specular surfaces using color. In: Proc. 2005 IEEE Computer society conference on computer vision and pattern recognition. IEEE, Los Alamitos, pp 210–224
Montes A, Salvador A, Pascual S, Giro-i Nieto X (2016) Temporal activity detection in untrimmed videos with recurrent neural networks. In: Proc. 1st NIPS workshop on large scale computer vision systems. NIPS, La Jolla, California, pp 1–5
Nayar S K, Fang X S, Boult T (1997) Separation of reflection components using color and polarization. Int J Comput Vis 21:163–186
Parkkinen J P S, Hallikainen J, Jaaskelainen T (1989) Characteristic spectra of munsell colors. J Opt Soc Am A 6:318–322
Pascanu R, Mikolov T, Bengio Y (2012) On the difficulty of training recurrent neural networks. https://arxiv.org/pdf/1211.5063.pdf. Accessed 28 May 2021
Sato Y, Ikeuchi K (1994) Temporal-color space analysis of reflection. J Opt Soc Am A 11:2990–3002
Schluns K, Koschan A (2000) Global and local highlight analysis in color images. In: Proc.1st.Int.Conf. Color Graphics Image Processing. Wiley, Hoboken, pp 300–304
Shafer S A (1985) Using color to separate reflection components. Color Res Appl 10:210–218
Shen H L, Zhang Z H (2013) Real-time highlight removal using intensity ratio. Appl Opt 52:4483–4493
Shen H L, Zhang H G, Shao S J (2008) Chromaticity-based separation of reflection components in a single image. Pattern Recogn 41:2461–2469
Suo J, An D, Ji X, Wang H, Dai Q (2016) Fast and high quality highlight removal from a single image. IEEE Trans Image Process 25:5441–5454
Tan R T, Ikeuchi K (2005) Separating reflection components of textured surfaces using a single image. IEEE Trans Pattern Anal Mach Intell 27:178–193
Tan P, Quan L, Lin S (2006) Separation of highlight reflections on textured surfaces. In: Proc. 2006 IEEE computer society conference on computer vision and pattern recognition. IEEE, Los Alamitos, pp 1855–1860
Vinod N, Hinton G E (2010) Rectified linear units improve restricted boltzmann machines. In: Proc. international conference on machine learning. ACM, New York, pp 807–814
Wang Z, Bovik AC, Sheikh HR, Simoncelli EP (2004) Image quality assessment: from error visibility to structural similarity. IEEE Trans Image Process 13:600–612
Wolff L B, Boult T E (1991) Constraining object features using a polarization reflectance model. IEEE Trans Pattern Anal Mach Intell 13:635–657
Yamamoto T, Nakazawa A (2019) General improvement method of specular component separation using high-emphasis filter and similarity function. ITE Trans Media Technol Appl 7:92–102
Yang Q X, Tan K H, Ahuja N (2009) Real-time o (1) bilateral filtering. In: Proc. 2009 IEEE computer society conference on computer vision and pattern recognition. IEEE, Los Alamitos, pp 557–564
Yang Q X, Wang S N, Ahuja N (2010) Real-time specular highlight removal using bilateral filtering. In: Proc. 2010 european conference on computer vision. Springer, New York, pp 87–100
Yang Q X, Tang J, Ahuja N (2015) Efficient and robust specular highlight removal. IEEE Trans Pattern Anal Mach Intell 37:1304–1311
Yoon K, Choi Y, Kweon I S (2006) Fast separation of reflection components using a specularity-invariant image representation. In: Proc. 2006 International conference on image processing. IEEE, Los Alamitos, pp 973–976
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Competing Interests
The authors declare that they have no competing interests.
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Chen, H., Luo, L., Guo, C. et al. Specular highlight removal using a divide-and-conquer multi-resolution deep network. Multimed Tools Appl 82, 36885–36907 (2023). https://doi.org/10.1007/s11042-023-14591-y
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-023-14591-y